Affordable and Portable Realtime Saudi License Plate Recognition using SoC

Stand along single board computers (SoC) have become so inexpensive and yet so powerful that paved the way for easily developing fully automated systems. SoC systems are equipped with sensors, cameras and various embedded systems that allow developing systems that interact with the surrounding environment. Therefore, the task of capturing images of License plates and using Optical Character Recognition (OCR) techniques to recognize the numerals and characters allows for developing an inexpensive License Plate (LP) Recognition system. LP systems are important and can be used for various application from traffic control, toll payment, and parking access. This paper proposes a Raspberry PI based LP recognition for Arabic/English Characters and Numeral on license plates used in Saudi Arabia. The proposed process utilizes the phases of Preprocessing, Segmentation, Feature Extraction and Classification. At the end of the preprocessing phase, the Characters and Numerals are segmented. Pixel distribution and Horizontal projection profiles are used in the feature extraction phase for the segmented image. Distance Classifier and k-nearest neighbors classifier are used in the classification phase. The proposed system achieved an accuracy of 90.6%. The advantage of such a system is the low cost and portability making it affordable and easily deployable in any location.